Enter opens the highlighted result. Esc closes.

DeepSeek V3.1 Terminus vs Qwen3.5 397B A17B

Qwen3.5 397B A17B leads DeepSeek V3.1 Terminus on the Artificial Analysis Intelligence Index, 21.4 to 14.8, and DeepSeek V3.1 Terminus costs 2.3x less per output token ($1.0142 vs $2.34 per million). Updated October 22, 2026; 38 benchmarks have a result for both.

Replace DeepSeek V3.1 Terminus Replace Qwen3.5 397B A17B
DeepSeek V3.1 TerminusDeepSeek
Coding
No data
Overall
No data
Output $/M
$1.0142
6
Qwen3.5 397B A17BQwen
Coding
No data
Overall
57.1
Output $/M
$2.34
32
vs boards won of 38 shared

DeepSeek V3.1 Terminus or Qwen3.5 397B A17B: which to pick

Neither model has a coding score yet, so the two cannot be ranked on coding.

Pick DeepSeek V3.1 Terminus for output tokens 2.3x cheaper ($1.0142 vs $2.34 per million) and work measured by SciCode or Terminal-Bench Hard (Artificial Analysis run), where it leads.

Model ADeepSeek V3.1 TerminusDeepSeekNot benchmarkedNo coding benchmarkNo cost per solved taskModel BQwen3.5 397B A17BQwenNot benchmarked1 independent benchmarkNo cost per solved task
Shared results
38
DeepSeek V3.1 Terminus only
7
Qwen3.5 397B A17B only
28
Like-for-like categories
8 of 9

Only benchmarks that tested both models count toward a pick; a result only one model has is shown but not compared.

Which one for your work

Each card is decided by one number both models carry. Where only one has it, the card says so and makes no call.

At a glance

Coding index
DeepSeek V3.1 Terminus not benchmarked, Qwen3.5 397B A17B not benchmarked.
Widest category
Agentic work, 58.5 points apart on average over 1 shared benchmark.
Widest single gap
τ²-Bench Telecom: DeepSeek V3.1 Terminus 37.1% against Qwen3.5 397B A17B 95.6%, 58.5 points apart on a 0 to 100 scale.
Output price
DeepSeek V3.1 Terminus $1.0142 against Qwen3.5 397B A17B $2.34 per million output tokens, 2.3x apart.
Context window
DeepSeek V3.1 Terminus takes 164K tokens, Qwen3.5 397B A17B 262K.

Benchmark by benchmark

First the score: boards each model leads, per category, where both have a result. Then every board, a category to a fold; bars are each result on a 0 to 100 scale, so compare the two in a row, not one row with another.

Boards won, where both have a result
CategoryDeepSeek V3.1 TerminusBarsQwen3.5 397B A17BTies
Coding14
Intelligence01
Agentic work01
Reasoning04
Math01
Knowledge22
Web design16
General213
All shared boards632
CodingLike-for-likeSix of these boards feed the Vibe Coding Index14
Coding benchmarks for DeepSeek V3.1 Terminus and Qwen3.5 397B A17B
BenchmarkDeepSeek V3.1 TerminusQwen3.5 397B A17BLeader
LMArena WebDevNot measured1400Only Qwen3.5 397B A17B measured
AA Coding Index43.5Not measuredOnly DeepSeek V3.1 Terminus measured
LiveCodeBench (Artificial Analysis run)79.8%Not measuredOnly DeepSeek V3.1 Terminus measured
SciCode38.0%44.8%Qwen3.5 397B A17B
Terminal-Bench Hard (Artificial Analysis run)31.8%40.9%Qwen3.5 397B A17B
ALE-Bench745.2621.9DeepSeek V3.1 Terminus
LMArena Text: coding14251464Qwen3.5 397B A17B
LMArena Text: software and IT14261463Qwen3.5 397B A17B
LMArena WebDev: ReactNot measured1388Only Qwen3.5 397B A17B measured
LMArena WebDev: HTMLNot measured1410Only Qwen3.5 397B A17B measured
Neither model has a result on the other 33 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index01
Intelligence benchmarks for DeepSeek V3.1 Terminus and Qwen3.5 397B A17B
BenchmarkDeepSeek V3.1 TerminusQwen3.5 397B A17BLeader
AA Intelligence Index14.821.4Qwen3.5 397B A17B
Epoch Capabilities IndexNot measured146.8Only Qwen3.5 397B A17B measured
Agentic workLike-for-likePublic boards, shown as published, kept out of the index01
Agentic work benchmarks for DeepSeek V3.1 Terminus and Qwen3.5 397B A17B
BenchmarkDeepSeek V3.1 TerminusQwen3.5 397B A17BLeader
AA Agentic Index6.8Not measuredOnly DeepSeek V3.1 Terminus measured
τ²-Bench Telecom37.1%95.6%Qwen3.5 397B A17B
APEX-AgentsNot measured24.9%Only Qwen3.5 397B A17B measured
Neither model has a result on the other 39 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index04
Reasoning benchmarks for DeepSeek V3.1 Terminus and Qwen3.5 397B A17B
BenchmarkDeepSeek V3.1 TerminusQwen3.5 397B A17BLeader
GPQA Diamond (Artificial Analysis run)79.2%89.3%Qwen3.5 397B A17B
Humanity's Last Exam (Artificial Analysis run)16.4%29.0%Qwen3.5 397B A17B
GPQA Diamond (Epoch AI run)Not measured86.4%Only Qwen3.5 397B A17B measured
Mystery game puzzlesNot measured18.0%Only Qwen3.5 397B A17B measured
LMArena Text: hard prompts14261448Qwen3.5 397B A17B
LMArena Text: expertNot measured1462Only Qwen3.5 397B A17B measured
LMArena Text: hard prompts in English14321450Qwen3.5 397B A17B
LMArena Vision: diagramsNot measured1277Only Qwen3.5 397B A17B measured
LMArena Vision: homeworkNot measured1292Only Qwen3.5 397B A17B measured
Kagi LLM Benchmark57.4%Not measuredOnly DeepSeek V3.1 Terminus measured
Neither model has a result on the other 13 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index01
Math benchmarks for DeepSeek V3.1 Terminus and Qwen3.5 397B A17B
BenchmarkDeepSeek V3.1 TerminusQwen3.5 397B A17BLeader
AA Math Index89.7Not measuredOnly DeepSeek V3.1 Terminus measured
AIME 2025 (Artificial Analysis run)89.7%Not measuredOnly DeepSeek V3.1 Terminus measured
OTIS Mock AIMENot measured88.9%Only Qwen3.5 397B A17B measured
FrontierMath, tiers 1 to 3Not measured31.2%Only Qwen3.5 397B A17B measured
LMArena Text: math14021453Qwen3.5 397B A17B
LMArena Text: mathematical workNot measured1454Only Qwen3.5 397B A17B measured
MathArenaNot measured19.2%Only Qwen3.5 397B A17B measured
Neither model has a result on the other 7 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index22
Knowledge benchmarks for DeepSeek V3.1 Terminus and Qwen3.5 397B A17B
BenchmarkDeepSeek V3.1 TerminusQwen3.5 397B A17BLeader
MMLU Pro (Artificial Analysis run)85.1%Not measuredOnly DeepSeek V3.1 Terminus measured
LMArena Text: science14511457Qwen3.5 397B A17B
LMArena Text: medicine and healthcare14681455DeepSeek V3.1 Terminus
LMArena Text: legal and government14571441DeepSeek V3.1 Terminus
LMArena Text: business and finance14141435Qwen3.5 397B A17B
Neither model has a result on the other 15 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index16
Web design benchmarks for DeepSeek V3.1 Terminus and Qwen3.5 397B A17B
BenchmarkDeepSeek V3.1 TerminusQwen3.5 397B A17BLeader
Design Arena: websites11871190Qwen3.5 397B A17B
Design Arena: UI components11801161DeepSeek V3.1 Terminus
Design Arena: game dev11311140Qwen3.5 397B A17B
Design Arena: data viz11681175Qwen3.5 397B A17B
Design Arena: 3D11411160Qwen3.5 397B A17B
Design Arena: all code categories11751179Qwen3.5 397B A17B
Design Arena: SVG10651139Qwen3.5 397B A17B
Neither model has a result on the other 2 boards here
GeneralLike-for-likePublic boards, shown as published, kept out of the index213
General benchmarks for DeepSeek V3.1 Terminus and Qwen3.5 397B A17B
BenchmarkDeepSeek V3.1 TerminusQwen3.5 397B A17BLeader
IFBench57.0%78.8%Qwen3.5 397B A17B
Long context reasoning (AA-LCR)69.3%77.3%Qwen3.5 397B A17B
DTBench81.3%87.5%Qwen3.5 397B A17B
LMCA28.6%37.9%Qwen3.5 397B A17B
LMArena Text14191437Qwen3.5 397B A17B
LMArena Text: instruction following14041424Qwen3.5 397B A17B
LMArena Text: creative writing14031402DeepSeek V3.1 Terminus
LMArena VisionNot measured1262Only Qwen3.5 397B A17B measured
LMArena Text: English14291443Qwen3.5 397B A17B
LMArena Text: non-English14081430Qwen3.5 397B A17B
LMArena Text: ChineseNot measured1498Only Qwen3.5 397B A17B measured
LMArena Text: GermanNot measured1445Only Qwen3.5 397B A17B measured
LMArena Text: JapaneseNot measured1429Only Qwen3.5 397B A17B measured
LMArena Text: KoreanNot measured1384Only Qwen3.5 397B A17B measured
LMArena Text: FrenchNot measured1462Only Qwen3.5 397B A17B measured
LMArena Text: SpanishNot measured1441Only Qwen3.5 397B A17B measured
LMArena Text: Russian14351430DeepSeek V3.1 Terminus
LMArena Text: Polish14271447Qwen3.5 397B A17B
LMArena Text: multi-turn14111446Qwen3.5 397B A17B
LMArena Text: longer queries14221441Qwen3.5 397B A17B
LMArena Text: writing and language14091415Qwen3.5 397B A17B
LMArena Text: entertainment and media13911399Qwen3.5 397B A17B
LMArena Vision: EnglishNot measured1268Only Qwen3.5 397B A17B measured
LMArena Vision: ChineseNot measured1314Only Qwen3.5 397B A17B measured
LMArena Vision: reading textNot measured1271Only Qwen3.5 397B A17B measured
LMArena Vision: humorNot measured1262Only Qwen3.5 397B A17B measured
LMArena Vision: captioningNot measured1230Only Qwen3.5 397B A17B measured
LMArena Vision: recognizing thingsNot measured1265Only Qwen3.5 397B A17B measured
LMArena Vision: creative writingNot measured1260Only Qwen3.5 397B A17B measured
Neither model has a result on the other 19 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for DeepSeek V3.1 Terminus and Qwen3.5 397B A17B
BenchmarkDeepSeek V3.1 TerminusQwen3.5 397B A17BLeader
Neither model has a result on 5 boards here

What each workload costs

Three fixed token mixes at each model's listed price, so per-token rates become a bill.

Chat turn

1K input + 500 output tokens

DeepSeek V3.1 Terminus$0.0008Fits in one request
Qwen3.5 397B A17B$0.0016Fits in one request

DeepSeek V3.1 Terminus costs less

Repository review

50K input + 3K output tokens

DeepSeek V3.1 Terminus$0.018Fits in one request
Qwen3.5 397B A17B$0.027Fits in one request

DeepSeek V3.1 Terminus costs less

Agent loop

200K input + 10K output tokens

DeepSeek V3.1 Terminus$0.071Exceeds the context window
Qwen3.5 397B A17B$0.101Fits in one request

DeepSeek V3.1 Terminus costs less

Listed OpenRouter rates, without cache or batch discounts. A workload that does not fit a model's context window would need splitting.

Specification differences

The leading value in a row is marked; a row with a missing value names no leader. Our two rows are marked in red.

Specifications of DeepSeek V3.1 Terminus and Qwen3.5 397B A17B
SpecificationDeepSeek V3.1 TerminusQwen3.5 397B A17B
MakerDeepSeekQwen
WeightsOpen weightsOpen weights
ReleasedSeptember 22, 2025February 16, 2026
Context window164K262K
Input $/Mtok$0.3063$0.39
Output $/Mtok$1.0142$2.34
Coding indexNot benchmarkedNot benchmarked
Independent measurements behind it01
Cost per solved taskNot computableNot computable
SourceOpenRouter listingOpenRouter listing

Questions

Is DeepSeek V3.1 Terminus better than Qwen3.5 397B A17B for coding?

Neither model has a coding score yet, so the two cannot be ranked on coding. Pick DeepSeek V3.1 Terminus for output tokens 2.3x cheaper ($1.0142 vs $2.34 per million) and work measured by SciCode or Terminal-Bench Hard (Artificial Analysis run), where it leads.

Which is cheaper, DeepSeek V3.1 Terminus or Qwen3.5 397B A17B?

DeepSeek V3.1 Terminus costs $0.3063 per million input tokens and $1.0142 per million output tokens; Qwen3.5 397B A17B costs $0.39 and $2.34. Cost per solved task is known for neither of them.

Which has the bigger context window, DeepSeek V3.1 Terminus or Qwen3.5 397B A17B?

Qwen3.5 397B A17B, with 262K tokens against 164K.

How many benchmarks is the DeepSeek V3.1 Terminus vs Qwen3.5 397B A17B comparison based on?

38 benchmarks have a result for both models as of October 22, 2026. DeepSeek V3.1 Terminus's coding index rests on 0 independent benchmarks and Qwen3.5 397B A17B's on 1. Where only one model has a result, the page says so instead of naming a winner.

Compare next